marinone94
commited on
Commit
β’
32a526a
1
Parent(s):
4807cf3
Training in progress, step 1400
Browse files- {checkpoint-1100 β checkpoint-1400}/config.json +0 -0
- {checkpoint-1100 β checkpoint-1400}/optimizer.pt +1 -1
- {checkpoint-1100 β checkpoint-1400}/preprocessor_config.json +0 -0
- {checkpoint-1100 β checkpoint-1400}/pytorch_model.bin +1 -1
- {checkpoint-1100 β checkpoint-1400}/rng_state.pth +2 -2
- {checkpoint-1100 β checkpoint-1400}/scaler.pt +1 -1
- {checkpoint-1100 β checkpoint-1400}/scheduler.pt +1 -1
- {checkpoint-1100 β checkpoint-1400}/trainer_state.json +120 -3
- {checkpoint-1100 β checkpoint-1400}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-1100 β checkpoint-1400}/config.json
RENAMED
File without changes
|
{checkpoint-1100 β checkpoint-1400}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490337809
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:066471e5b1e42d95f381420c5eb456280eaebbcce841ac5387ae7bfde1fc9de6
|
3 |
size 2490337809
|
{checkpoint-1100 β checkpoint-1400}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-1100 β checkpoint-1400}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a459f72ab853af3d30be6993d7c2796ebd50d28c9cae60928258ccc702d6e46
|
3 |
size 1262063089
|
{checkpoint-1100 β checkpoint-1400}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1f4e020badfa95b92140e362fadf8866d696357e6c8984f31eba89adcf57045
|
3 |
+
size 14631
|
{checkpoint-1100 β checkpoint-1400}/scaler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26339048a0b88d77fc1a5e9abedb9d0653c3cd4b707b2f8b4a992e2612d53b7f
|
3 |
size 559
|
{checkpoint-1100 β checkpoint-1400}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce6cad226e370a6c6a2392ca8fc4c8eed33526e65dfa1b9d115b105ea51c8462
|
3 |
size 623
|
{checkpoint-1100 β checkpoint-1400}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -435,11 +435,128 @@
|
|
435 |
"eval_steps_per_second": 0.78,
|
436 |
"eval_wer": 0.37964802724950325,
|
437 |
"step": 1100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
438 |
}
|
439 |
],
|
440 |
"max_steps": 4550,
|
441 |
"num_train_epochs": 50,
|
442 |
-
"total_flos":
|
443 |
"trial_name": null,
|
444 |
"trial_params": null
|
445 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.382513661202186,
|
5 |
+
"global_step": 1400,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
435 |
"eval_steps_per_second": 0.78,
|
436 |
"eval_wer": 0.37964802724950325,
|
437 |
"step": 1100
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 12.31,
|
441 |
+
"learning_rate": 0.00014000000000000001,
|
442 |
+
"loss": 1.3478,
|
443 |
+
"step": 1120
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 12.52,
|
447 |
+
"learning_rate": 0.0001425,
|
448 |
+
"loss": 1.3164,
|
449 |
+
"step": 1140
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 12.74,
|
453 |
+
"learning_rate": 0.000145,
|
454 |
+
"loss": 1.269,
|
455 |
+
"step": 1160
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 12.96,
|
459 |
+
"learning_rate": 0.0001475,
|
460 |
+
"loss": 1.2292,
|
461 |
+
"step": 1180
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 13.19,
|
465 |
+
"learning_rate": 0.00015,
|
466 |
+
"loss": 1.2229,
|
467 |
+
"step": 1200
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 13.19,
|
471 |
+
"eval_loss": 0.28933778405189514,
|
472 |
+
"eval_runtime": 192.6398,
|
473 |
+
"eval_samples_per_second": 25.14,
|
474 |
+
"eval_steps_per_second": 0.789,
|
475 |
+
"eval_wer": 0.26520011353959694,
|
476 |
+
"step": 1200
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 13.4,
|
480 |
+
"learning_rate": 0.0001525,
|
481 |
+
"loss": 1.182,
|
482 |
+
"step": 1220
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 13.62,
|
486 |
+
"learning_rate": 0.000155,
|
487 |
+
"loss": 1.1768,
|
488 |
+
"step": 1240
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 13.84,
|
492 |
+
"learning_rate": 0.0001575,
|
493 |
+
"loss": 1.1534,
|
494 |
+
"step": 1260
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 14.07,
|
498 |
+
"learning_rate": 0.00016,
|
499 |
+
"loss": 1.1832,
|
500 |
+
"step": 1280
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 14.28,
|
504 |
+
"learning_rate": 0.00016250000000000002,
|
505 |
+
"loss": 1.1106,
|
506 |
+
"step": 1300
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 14.28,
|
510 |
+
"eval_loss": 0.24685777723789215,
|
511 |
+
"eval_runtime": 198.5067,
|
512 |
+
"eval_samples_per_second": 24.397,
|
513 |
+
"eval_steps_per_second": 0.766,
|
514 |
+
"eval_wer": 0.2253760999148453,
|
515 |
+
"step": 1300
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 14.5,
|
519 |
+
"learning_rate": 0.000165,
|
520 |
+
"loss": 1.1217,
|
521 |
+
"step": 1320
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 14.72,
|
525 |
+
"learning_rate": 0.0001675,
|
526 |
+
"loss": 1.1236,
|
527 |
+
"step": 1340
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 14.94,
|
531 |
+
"learning_rate": 0.00017,
|
532 |
+
"loss": 1.0969,
|
533 |
+
"step": 1360
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 15.16,
|
537 |
+
"learning_rate": 0.0001725,
|
538 |
+
"loss": 1.0971,
|
539 |
+
"step": 1380
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 15.38,
|
543 |
+
"learning_rate": 0.000175,
|
544 |
+
"loss": 1.0663,
|
545 |
+
"step": 1400
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 15.38,
|
549 |
+
"eval_loss": 0.22192780673503876,
|
550 |
+
"eval_runtime": 189.4566,
|
551 |
+
"eval_samples_per_second": 25.563,
|
552 |
+
"eval_steps_per_second": 0.802,
|
553 |
+
"eval_wer": 0.19727504967357365,
|
554 |
+
"step": 1400
|
555 |
}
|
556 |
],
|
557 |
"max_steps": 4550,
|
558 |
"num_train_epochs": 50,
|
559 |
+
"total_flos": 2.168370158639202e+19,
|
560 |
"trial_name": null,
|
561 |
"trial_params": null
|
562 |
}
|
{checkpoint-1100 β checkpoint-1400}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a459f72ab853af3d30be6993d7c2796ebd50d28c9cae60928258ccc702d6e46
|
3 |
size 1262063089
|